Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,694 papers · 148 categories

Trend · papers per month

17335066 · Jun 202019922001200920172026
48 results for Group-equivariant autoencoder

GE-autoencoder identifies spontaneous symmetry breaking in systems.

problem Locating phase boundaries and identifying spontaneously broken symmetries in systems.
method Group-equivariant autoencoder using group theory to constrain parameters and learn invariant order parameters.
result GE-autoencoder accurately determines spontaneous symmetry breaking and estimates critical temperatures more efficiently.

The paper studies geometric properties of group equivariant operators and their Riemannian structure.

problem Understanding the geometric structure of group equivariant operators.
method Endowing the space of group equivariant non-expansive operators with a Riemannian manifold structure and using gradient descent methods.
result Gradient descent methods can be applied to minimize cost functions on the space of group equivariant non-expansive operators.

Characterizes group-equivariant neural networks for three groups.

problem Understanding equivariant neural networks for orthogonal, special orthogonal, and symplectic groups.
method Characterized all possible group-equivariant neural networks for three groups.
result Found spanning sets of matrices for learnable, linear equivariant layer functions.

The paper shows how data augmentation and regularization can enforce group equivariance in machine learning models.

problem Improving model performance by leveraging known symmetries in machine learning tasks.
method Training with data augmentation and regularization to enforce group equivariance.
result Equivariance of the trained model can be achieved through training on augmented data in tandem with regularization.

Group equivariant neural networks simplify complex tasks with group representation theory.

problem Challenging tasks requiring input transformations like rotations.
method Group representation theory, non-commutative harmonic analysis, differential geometry.
result A neural network is group equivariant if and only if it has a convolutional structure.

Category theory enhances understanding of group-equivariant neural networks.

problem Understanding and working with group-equivariant neural networks.
method Application of category theory to tensor power spaces of Rn\mathbb{R}^{n} for groups SnS_n, O(n)O(n), Sp(n)Sp(n), and SO(n)SO(n).
result New insights and an algorithm for computing equivariant linear layers.

Although group convolutional networks are able to learn powerful representations based on symmetry patterns, they lack explicit means to learn meaningful relationships among them (e.g., relative positions and poses). In this paper, we present attentive group equivariant convolutions, a generalization of the group convo…

2020-02-07abs ↗pdf ↗

Paper defines mathematical framework for neural network explainability.

problem Neural network explainability and equivariant operators.
method Mathematical framework based on Group Equivariant Non-Expansive Operators (GENEOs) and complexity measures.
result Formal properties and interpretability of Group Equivariant Operators (GEOs) defined.

SymPE breaks symmetries in equivariant networks, improving performance across various tasks.

problem Equivariant networks cannot break symmetries, leading to poor performance in tasks with symmetrical inputs.
method Novel equivariant conditional distributions and randomized canonicalization.
result SymPE significantly improves performance of group-equivariant and graph neural networks.

New algorithm speeds up group equivariant neural networks computations.

problem Challenging computations in group equivariant neural networks.
method Diagrammatic framework based on category theory for matrix multiplication.
result Exponential improvement in time complexity for matrix multiplication.

We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a natural generalization of convolutional neural networks that reduces sample complexity by exploiting symmetries. G-CNNs use G-convolutions, a new type of layer that enjoys a substantially higher degree of weight sharing than regular convolution la…

2016-02-24abs ↗pdf ↗

Characterizes a specific type of neural network for alternating group equivariance.

problem Understanding and characterizing neural networks with alternating group equivariance.
method Characterization of all possible AnA_n-equivariant neural networks using tensor powers of Rn\mathbb{R}^{n}.
result Found a basis of matrices for learnable, linear AnA_n-equivariant layer functions.

Paper shows mapping class group-equivariant Teichmüller space deformation to Thurston spine.

problem Mapping Teichmüller space to Thurston spine.
method Equivariant deformation retraction of Teichmüller space onto a cell complex.
result Thurston spine contains points corresponding to hyperbolic surfaces with shortest geodesics forming polygons.

L-CNNs maintain gauge symmetry on non-Abelian lattice theories.

problem Applying convolutional neural networks to non-Abelian lattice gauge theories while preserving gauge symmetry.
method Developed a geometric formulation of L-CNNs that are equivariant under global symmetries and gauge transformations.
result Convolutional operations in L-CNNs are a specific case of gauge-equivariant neural networks on SU(NN) principal bundles.

New method finds Lie group representations without explicit groups, enabling new neural network architectures.

problem Building neural networks equivariant to arbitrary Lie groups.
method Algorithm to find Lie group representations from Lie algebra structure constants. Self-contained method for constructing Lie group-equivariant neural networks.
result First object-tracking model equivariant to the Poincaré group.

GNPE improves inference for astrophysical systems.

problem Efficiently incorporating geometric properties like equivariances in neural density estimation.
method GNPE integrates equivariances into neural posterior estimation, standardizing data pose while estimating parameters.
result GNPE achieves state-of-the-art accuracy in astrophysical binary black hole inference, reducing inference times by 3 orders of magnitude.

SCENE-Net improves 3D point cloud segmentation with low resource usage and transparency.

problem Lack of resources and transparency in 3D semantic segmentation models.
method SCENE-Net uses signature shapes identified via GENEOs to achieve semantic segmentation with minimal resources.
result SCENE-Net achieves comparable IoU to state-of-the-art methods with less data and computational resources.

Optimal classification requires choosing the right group symmetries, contrary to intuition.

problem Improving binary classification performance by selecting appropriate group symmetries.
method Developed a theoretical framework for designing group equivariant neural networks.
result Optimal classification performance is achieved by selecting the appropriate subgroups of symmetries, not the largest equivariant groups.

This note is mostly an exposition of an unpublished result of Deligne, which introduces an analogue of perverse tt-structure on the derived category of coherent sheaves on a Noetherian scheme with a dualizing complex. Construction extends to the category of coherent sheaves equivariant under an action of an algebraic …

2000-05-16abs ↗pdf ↗

Lisa Jeffrey and Frances Kirwan developed an integration theory for symplectic reductions. That is, given a symplectic manifold with symplectic group action, they developed a way of pulling the integration of forms on the reduction back to an integration of group-equivariant forms on the original space. We seek an anal…

2004-02-18abs ↗pdf ↗

Characterizes area-minimizing maps for surfaces of genus ≥ 2.

problem Equivariant area-minimizing maps on surface covers.
method Classifies minimal surfaces in Hilbert spheres with constant negative Gaussian curvature.
result Characterizes all equivariantly area-minimizing maps from the universal cover of a surface to a Hilbert sphere.

We present a PDE-based framework that generalizes Group equivariant Convolutional Neural Networks (G-CNNs). In this framework, a network layer is seen as a set of PDE-solvers where geometrically meaningful PDE-coefficients become the layer's trainable weights. Formulating our PDEs on homogeneous spaces allows these net…

2020-01-24abs ↗pdf ↗

Feature extraction becomes increasingly important as data grows high dimensional. Autoencoder as a neural network based feature extraction method achieves great success in generating abstract features of high dimensional data. However, it fails to consider the relationships of data samples which may affect experimental…

2018-02-09abs ↗pdf ↗

Proposes a Bayesian Autoencoder with sparse Gaussian process priors to capture data correlations.

problem Autoencoders' i.i.d. assumption of latent representations fails to capture data correlations.
method Imposes fully Bayesian sparse Gaussian Process priors on the latent space of a Bayesian Autoencoder and uses stochastic gradient Hamiltonian Monte Carlo for posterior estimation.
result Consistently outperforms alternatives relying on Variational Autoencoders on various tasks.

The paper investigates how symmetry in models affects their performance and generalization.

problem Understanding how symmetry in models impacts their performance and generalization.
method Formal unified investigation of intuitions about symmetry in models and data.
result Quantitative bounds and comparisons between model and data equivariance lead to optimal model performance.

Study on dynamics of non-linear autoencoders learning principal components.

problem Technical difficulty in studying non-linear autoencoders due to non-trivial correlations.
method Derive asymptotically exact equations for SGD training of shallow, non-linear autoencoders.
result Autoencoders learn principal components sequentially and tie weights are ineffective.

A new algorithmic framework is proposed for learning autoencoders of data distributions. We minimize the discrepancy between the model and target distributions, with a \emph{relational regularization} on the learnable latent prior. This regularization penalizes the fused Gromov-Wasserstein (FGW) distance between the la…

2020-02-07abs ↗pdf ↗

Chart autoencoders learn latent features preserving manifold topology and geometry, with robust denoising capabilities.

problem Learning low-dimensional latent features of high-dimensional data sampled near a manifold.
method Chart autoencoders encode data into latent features on charts, preserving manifold topology and geometry.
result Chart autoencoders achieve a squared generalization error of n2d+2log4nn^{-\frac{2}{d+2}}\log^4 n under proper network architectures.